© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14612
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to technology and its implications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ждении
    -0.61
     DriverManager
    -0.58
     difesa
    -0.58
    AdapterFactory
    -0.56
     fédé
    -0.56
    msford
    -0.56
    Demografía
    -0.55
    šanai
    -0.55
    GEBURTS
    -0.54
     commerciaux
    -0.54
    POSITIVE LOGITS
     ModelExpression
    0.79
    NameInMap
    0.69
    }}],
    0.68
    تقاوى
    0.65
     CreateTagHelper
    0.65
     suges
    0.63
    setVerticalGroup
    0.61
     disponibilités
    0.60
    IUrlHelper
    0.58
    aires
    0.57
    Activations Density 0.076%

    No Known Activations